Hello there and thanks for checking out this workflow!
What's new in v11? : Major Changes; rework of the entire workflow to utilize SubGraphs!
—Purpose—
Built to provide a versatile and modular all-in-one workflow for SDXL/Pony/llustrious and SD15 streamlining the most useful features focused on efficiency and structure.
—Features—
Full metadata; recognized by CivitAI
LoRA loaders
Wildcard prompting
ControlNet
IPAdapter + FaceID
Installation and download guide for models and nodes
Multiple passes with optional upscales
— 1st : Detail Daemon Sampling + Variation Seed
— 2nd : Detail Daemon + PAG + Tiled Diffusion or UltimateSDUpscale
— ADetailer
— Inpainting
—Custom Nodes—
All of which can be installed through the ComfyUI-Manager
—Troubleshooting—
If nodes show up red (failing to load), check the 'Install Missing Custom Nodes' tab of the ComfyUI Manager for the missing node packs and install them.
Please check if all custom node packs load properly after installing, i.e. no
(IMPORT FAILED)messages next to any of them in the console upon ComfyUI startup.Always reload/drag'n'drop the original, downloaded workflow file into ComfyUI to reload an intact version of the workflow.
→ The last opened workflow that appears on startup only shows a cached version.
—Thanks—
The workflow would not be possible as is without these custom node packs. If you want to support the custom node creators, give them a ⭐ on their github repos! Thank you!
Feel free to ask any questions, share improvements or suggestions in the comment section!
Also let me know if you encounter any confusing points I can elaborate on and focus on improving for the next update!
Description
v10
- Structural changes
- Addition of Advanced Settings to expand on the model loading options and allow use of custom CLIP models
- Addition of Variation Seed feature to 1st Pass
- Addition of Pass Input Hijack section allowing loaded images to act as 1st/2nd Pass result
- Rework of Metadata collection
- Rework of LoRA Settings group
- Custom node pack changes :
- : ComfyUI-List-Utils
+ : ComfyUI-Inspire-Pack
v10.1
- Fixed broken scheduler selector node
FAQ
Comments (4)
Hi, Why do you prefer SDXL over FLUX for most of your AI art, despite FLUX's popularity? Just wondering, because i see this switch with a lot of AI users that has a massive post count.
Hey there, I didn't really notice posting so much more SDXL content over Flux to be honest.
I think that especially with the advent of SVDQuantizations Flux has become a lot more accessible to users with lower VRAM, while speeding up generation times for everyone else, so I'd expect more of an up-trend in terms of Flux use, if SVDQs get a little more love and polish.
But I do find Flux more limited in its stylistic range, probably due to its relative inflexibility in terms of training from what I read, which is why there's just a far greater amount of uniquely stylized models for SDXL, especially including the Pony, Illustrious derivatives as well, while also having more convenient and cheaper training options.
Hi, thanks for providing an amazing workflow. Can you also please share the guide how to use and properly utilize the true potential of this workflow? If you have already made a guide or video, please do share. Thanks.
Hey there, thank you very much! Glad you like it 🙏🏻
A new version is scheduled to be up in a few hours which should be much simpler to navigate and use. Converting many parts of the workflow into subgraphs not only saved a lot of space, but also allowed concentrating important settings to be accessible in one node.
Due to the amount of changes with each update video guides would be outdated within weeks, sometimes even days. But I try to keep all the INFO boxes updated and as informative and succinct as possible to serve as a form of manual.
But if you find any particular nodes/sections confusing or the attached INFO documentation lacking, feel free to let me know and I'll try to clarify and improve it 👌



















